Enhanced sensor health and regression testing for vehicles
Devices, systems, and methods are provided for sensor health and regression testing. A sensor testing system may include a first plurality of sensor testing targets positioned on a first side of a vehicle at a first distance from the vehicle, a second plurality of sensor testing targets positioned on a second side of the vehicle at the first distance, and a first sensor testing target positioned at a second distance from the vehicle, the second distance further from the vehicle than the first distance. The first and second pluralities of sensor testing targets both may include three or more sensor testing targets for testing cameras and light detection and ranging (LIDAR) sensors of the vehicle. The first sensor testing target may be used to test at least one of camera or LIDAR data. The sensor testing system may identify degradation of sensor performance, triggering further analysis and/or repairs.
Latest Argo AI, LLC Patents:
- Systems and methods for trajectory based
- Automatic generation of vector map for vehicle navigation
- Devices, systems, and methods for mitigating vehicle power loss in battery mode
- Methods and system for predicting trajectories of actors with respect to a drivable area
- Method and system for forecasting reactions of other road users in autonomous driving
This disclosure generally relates to systems and methods for sensor testing.
BACKGROUNDSome vehicles are equipped with a sensor system to collect data relating to the current and developing state of the vehicle's surroundings. The proper performance of a vehicle depends on the accuracy data collected by the sensors in the sensor system. The sensor system may comprise radars, visual spectrum cameras, laser-ranging devices (LIDARs), thermal sensors, or other types of sensors. The sensor system enables a vehicle to detect objects and obstacles in the vicinity of the vehicle and tracks the velocity and direction of pedestrians, other vehicles, traffic lights, or similar objects in the environment around the vehicle.
However, sensor performance may degrade over time, undermining the experience of passengers of vehicles that use a sensor system.
Certain implementations will now be described more fully below with reference to the accompanying drawings, in which various implementations and/or aspects are shown. However, various aspects may be implemented in many different forms and should not be construed as limited to the implementations set forth herein; rather, these implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Like numbers in the figures refer to like elements throughout. Hence, if a feature is used across several drawings, the number used to identify the feature in the drawing where the feature first appeared will be used in later drawings.
DETAILED DESCRIPTIONVehicle fleets, such as fleets of autonomous vehicles, may have sensor systems that use cameras, light detection and ranging (LIDAR), radar, and/or thermal sensors to detect objects and control vehicle operations. The sensors may be tested for performance standards before the vehicles are used in the field (e.g., to transport people). Once the vehicles are driving (e.g., in use), there may not be a way to monitor sensor performance over time. Because sensor performance may decline over time, if sensor performance is not tracked, vehicle operation may be impacted, and may undermine user experience. For example, sensor detection may control the acceleration and deceleration of a vehicle, so when a sensor detects the presence of an object, the vehicle may slow down and stop. A degraded sensor performance may result in “harder” deceleration (e.g., faster rate of deceleration) of the vehicle, which may be less comfortable for a vehicle passenger than a smoother (e.g., slower) deceleration.
Therefore, vehicles and vehicle passengers may benefit from proactive monitoring and predicting of sensor performance to identify possible future sensor degradation before the degradation may occur.
Example embodiments described herein provide certain systems, methods, and devices for a sensor testing.
In one or more embodiments, a vehicle sensor testing system may be established to test vehicle sensors, identify sensor data trends from sensor data of multiple vehicles, and predict when sensor degradation may occur for any vehicle. The sensor testing system may a vehicle depot location to where autonomous vehicles may drive and have vehicle sensors tested. For example, the sensor testing system may be a drive-through depot. As a vehicle drives through the depot, various scans and other tests may be performed on the vehicle sensors. The vehicle sensor tests may provide data indicative of the health of any sensor of any vehicle.
In one or more embodiments, the vehicle sensor testing system may identify when a sensor's data exhibits signs of possible degradation. For example, when a sensor's data does not satisfy one or more thresholds, and/or matches sensor data trends (e.g., based on a corpus of sensor data from one or more vehicles over time) that are indicative of possible degradation, the vehicle sensor testing system proactively may repair or replace sensors before sensor performance declines.
In one or more embodiments, the vehicle sensor testing system may allow a vehicle to drive into an area of the depot (e.g., a testing area) where sensor testing targets may be arranged around the vehicle at one or more distances from the vehicle (e.g., in a circle around the vehicle). The testing targets may allow for vehicle sensors using different modalities (e.g., camera, LIDAR, radar, thermal, etc.) to detect objects and their distances from the vehicle. For example, the vehicle sensor testing system may measure the spatial frequency response (SFR), dynamic range, and color accuracy of a vehicle camera, and may determine a perception-based image quality evaluator (PIQE) score of a vehicle camera. The vehicle sensor testing system may measure noise, range, intensity, probability of detection, and other metrics for LIDAR sensors. Based on the sensor data for any sensor type, the vehicle sensor testing system may determine when sensor degradation may occur.
In one or more embodiments, the vehicle sensor testing system may include multiple testing targets for the vehicle sensors. Some testing targets may be used for sensors of different modalities, and other testing targets may be used for one sensor modality, but not another sensor modality (e.g., a LIDAR sensor may ignore a camera testing target). The testing targets may use varying designs. For example, a camera testing target may include different color patches and/or slanted edges patches. A LIDAR testing target may include alternating regions of high and low reflectivity (e.g., a zebra/referee-striped testing target). Testing targets may be combined. For example, the camera testing target with color patches may be incorporated into the LIDAR testing target with referee stripes.
In one or more embodiments, the vehicle sensor testing system may collect sensor data from multiple vehicles. When a vehicle event occurs, such as a hard deceleration (e.g., a deceleration that exceeds a threshold value), the vehicle sensor testing system may evaluate sensor data for one or more sensors of the vehicle that experienced the event to identify any data trends preceding the event. The vehicle sensor testing system may identify increasing or decreasing sensor data metrics over time that may indicate performance degradation. For example, when evaluating camera SFR data over time, the vehicle sensor testing system may identify SFR data points over time that may indicate a decrease on SFR that may be indicative of degradation. When evaluating LIDAR data over time, the vehicle sensor testing system may identify increasing noise in a particular laser channel, and the increasing noise may indicate degradation.
In one or more embodiments, the vehicle sensor testing system may compare sensor data trends from sensors of different vehicles that experience the same or similar events, and may determine data patterns indicative of future sensor degradation that may cause the occurrence of events. When the vehicle sensor testing system performs sensor testing on a vehicle at the depot, the vehicle sensor testing system may determine whether the sensor data and any prior sensor data for a respective sensor matches a data pattern that has been associated with an event. When vehicle sensor data matches a data pattern that has been associated with an event, the vehicle sensor testing system may predict that a sensor may degrade at a time in the future, and may trigger further evaluation, repair, or replacement of a sensor. The vehicle sensor testing system also may trigger communications to other vehicles in a same vehicle fleet as the vehicle whose sensor is predicted to experience degradation, and the communications may cause the fleet vehicles to drive to the depot for sensor testing.
In one or more embodiments, the vehicle sensor testing system may use minimum criteria thresholds that, when not satisfied by sensor data, may indicate that future degradation may occur. Even when vehicle sensor data satisfies a minimum criteria threshold, however, the vehicle sensor testing system may evaluate sensor data for any sensor over time to identify whether the data trends indicate an increase or decrease over time, or match any patterns that are associated with known vehicle events. When vehicle sensor data fail to satisfy a minimum criteria threshold, the vehicle sensor testing system may trigger further evaluation, repair, or replacement of a sensor.
The above descriptions are for purposes of illustration and are not meant to be limiting. Numerous other examples, configurations, processes, etc., may exist, some of which are described in greater detail below. Example embodiments will now be described with reference to the accompanying figures.
Referring to
In one or more embodiments, the sensor system 110 may include LIDAR 122. Some examples of a LIDAR may include Geiger mode LIDAR, ground-based LIDAR, large footprint LIDAR, small footprint LIDAR, or the like. The sensor system 110 may include cameras 124 such as stereo cameras that may capture images in the vicinity of the vehicle 102. The sensor system 110 may include a thermal sensor 126, such as far infrared imaging cameras, thermistors, resistance temperature detectors, thermocouples, semiconductors, or the like. Further, the sensor system may include a radar 128, which may be any radar that uses radio waves to capture data from objects surrounding the vehicle 102. The sensor system 110 may also include one or more processors 132. The one or more processors 132 may control the transmission and reception of signals using the LIDAR 122, the cameras 124, the thermal sensor 126, and the radar 128. The various sensors of the sensor system 110, when calibrated correctly, should indicate a proper distance and shape of object 152.
In one or more embodiments, any of the LIDAR 122, the cameras 124, the thermal sensor 126, and the radar 128 of the sensor system 110 may degrade over time, undermining user experience (e.g., the experience of a passenger of the vehicle 102). A vehicle sensor testing system (e.g., as shown in
In one or more embodiments, the sensor system 110 optionally may include one or more additional sensors 134, such as acoustic sensors (e.g., microphones, ultrasonic sensors, etc. for detecting acoustic data for the vehicle 102) and/or other sensors that may detect objects and/or conditions of the environment in which the vehicle 102 operates (e.g., detection of sounds, objects, people, weather, and the like), allowing the vehicle 102 to operate (e.g., change speeds, direction, driving modes, etc.).
It is understood that the above descriptions are for purposes of illustration and are not meant to be limiting.
Referring to
Still referring to
In one or more embodiments, as the vehicle 102 drives through the testing environment 202, various scans and other tests may be performed on the vehicle sensors. The vehicle sensor tests may provide data indicative of the health of any sensor of any vehicle.
In one or more embodiments, the system 200 may identify when a sensor's data exhibits signs of possible degradation. For example, when a sensor's data does not satisfy one or more thresholds (e.g., as determined by the one or more sensor health modules 250), and/or matches sensor data trends (e.g., as determined by the one or more pattern matching modules 248 based on the sensor data 246 and the event data 242) that are indicative of possible degradation, the system 200 proactively may repair or replace sensors before sensor performance declines.
In one or more embodiments, the testing targets may allow for vehicle sensors using different modalities (e.g., camera, LIDAR, radar, thermal, etc.) to detect objects and their distances from the vehicle 102. For example, the vehicle sensor testing system may measure SFR data, dynamic range data, color measurements, blur, noise, PIQE scores, distance measurements, frequency channels, elevation, hits per target, range accuracy and precision, intensity accuracy and precision, probability of detection (e.g., detecting a target), and the like. Based on the sensor data for any sensor type, the one or more sensor health modules 250 may determine when sensor degradation may occur.
In one or more embodiments, the sensor testing targets may provide different types of data. For example, the far field target 218 may be used to detect SFR, dynamic range, and color accuracy (e.g., using patches as shown in
In one or more embodiments, the one or more computers 230 may collect the sensor data 246 from multiple vehicles. When a vehicle event occurs, the one or more computers 230 may evaluate the sensor data 246 for one or more sensors of the vehicle that experienced the event to identify any data trends preceding the event. The one or more computers 230 may identify increasing or decreasing sensor data metrics over time that may indicate performance degradation. For example, when evaluating camera SFR data over time, the one or more computers 230 may identify SFR data points over time that may indicate a decrease on SFR that may be indicative of degradation. When evaluating LIDAR data over time, the one or more computers 230 may identify increasing noise in a particular channel, and the increasing noise may indicate degradation.
In one or more embodiments, the one or more pattern matching modules 248 may compare sensor data trends from sensors of different vehicles that experience the same or similar events, and may determine data patterns indicative of future sensor degradation that may cause the occurrence of events. When the system 200 performs sensor testing on the vehicle 102, the one or more pattern matching modules 248 may determine whether the sensor data 246 matches a data pattern that has been associated with an event. When the sensor data 246 matches a data pattern that has been associated with an event, the one or more sensor health modules 250 may predict that a sensor may degrade at a time in the future, and may trigger further evaluation, repair, or replacement of a sensor. The one or more computers 230 also may trigger communications 260 to other vehicles 270 in a same vehicle fleet as the vehicle whose sensor is predicted to experience degradation, and the communications may cause the fleet vehicles 270 to drive to the testing environment 202 for sensor testing.
In one or more embodiments, the one or more sensor health modules 250 may use minimum criteria thresholds that, when not satisfied by the sensor data 246, may indicate that future degradation may occur. Even when vehicle sensor data satisfies a minimum criteria threshold, however, the one or more pattern matching modules 248 may evaluate the sensor data 246 for any sensor over time to identify whether the data trends indicate an increase or decrease over time, or match any patterns that are associated with known vehicle events. When vehicle sensor data fail to satisfy a minimum criteria threshold, the one or more computers 230 may trigger further evaluation, repair, or replacement of a sensor.
It is understood that the above descriptions are for purposes of illustration and are not meant to be limiting.
Referring to
It is understood that the above descriptions are for purposes of illustration and are not meant to be limiting.
Referring to
It is understood that the above descriptions are for purposes of illustration and are not meant to be limiting.
Referring to
In one or more embodiments, any of the testing targets shown in
It is understood that the above descriptions are for purposes of illustration and are not meant to be limiting.
Referring to
It is understood that the above descriptions are for purposes of illustration and are not meant to be limiting.
Referring to
At block 502, a device (e.g., or system, such as the system 200 of
At block 504, the device may receive second camera data associated with a second camera of the vehicle, and based on image data captured for a sensor testing target of the second plurality of sensor testing targets. For example, the second camera data may include data used to determine SFR, dynamic range, and color accuracy of a vehicle camera, and image quality evaluator scores of a vehicle camera. The first and second testing targets may be at a same distance from the vehicle (e.g., the radius r of
At block 506, the device may receive first LIDAR data for a first LIDAR sensor of the vehicle. The first LIDAR data may be detected based on the reflection of emitted light from vehicle LIDAR, and the reflection off of a third sensor testing target (e.g., of the first plurality of sensor testing targets) may be used to determine LIDAR data metrics such as noise, range, intensity, probability of detection, and other metrics.
At block 508, the device may receive second LIDAR data for a second LIDAR sensor of the vehicle. The second LIDAR data may be detected based on the reflection of emitted light from vehicle LIDAR, and the reflection off of a fourth sensor testing target (e.g., of the second plurality of sensor testing targets) may be used to determine LIDAR data such as noise, range, intensity, probability of detection, and other metrics.
At block 510, the device may receive third camera data for a third camera of the vehicle and/or may receive third LIDAR data for a third LIDAR sensor of the vehicle. The third camera data and/or LIDAR data may be based on a fifth sensor testing target and/or sixth sensor testing target (e.g., the far field target 218 and/or the long distance target 220 of
At block 512, the device may determine, based on any of the camera and/or LIDAR data of blocks 502-510, that a sensor of the vehicle has failed to satisfy a vehicle performance metric and/or matches a data trend associated with a vehicle event. For example, the device may measure the SFR, dynamic range, and color accuracy of a vehicle camera, and may determine image quality evaluator scores of a vehicle camera, and when such performance metrics are above or below a threshold metric/score, the sensor whose data is above or below the threshold may be identified as failing to satisfy the vehicle performance metric. The device may measure noise, range, intensity, probability of detection, and other metrics for LIDAR sensors. When a LIDAR sensor's noise exceeds a threshold noise, the probability of detection is below a threshold probability, the range is below a threshold range, or the intensity is below a threshold intensity, the LIDAR sensor may be identified as failing to satisfy the vehicle performance metric. Any one or multiple sensors may be identified as failing to satisfy the vehicle performance metric. Alternatively or in addition, the device may identify that a trend (e.g., an increase or decrease) in the camera and/or LIDAR data of blocks 502-510 may match trends that have been associated with vehicle events (e.g., sudden stops, changes in direction, etc.), and the matching trend may indicate that a sensor is degrading and may result in a same or similar vehicle event.
At block 514, the device may cause presentation of an indication that the cameras and/or LIDAR sensors of the vehicle are failing to satisfy the vehicle performance metric and/or match a vehicle event trend. For example, the outputs presented in
It is understood that the above descriptions are for purposes of illustration and are not meant to be limiting.
For example, the computing system 600 of
Processor bus 612, also known as the host bus or the front side bus, may be used to couple the processors 602-606 and/or the one or more sensor testing devices 609 with the system interface 624. System interface 624 may be connected to the processor bus 612 to interface other components of the system 600 with the processor bus 612. For example, system interface 624 may include a memory controller 618 for interfacing a main memory 616 with the processor bus 612. The main memory 616 typically includes one or more memory cards and a control circuit (not shown). System interface 624 may also include an input/output (I/O) interface 620 to interface one or more I/O bridges 625 or I/O devices 630 with the processor bus 612. One or more I/O controllers and/or I/O devices may be connected with the I/O bus 626, such as I/O controller 628 and I/O device 630, as illustrated.
I/O device 630 may also include an input device (not shown), such as an alphanumeric input device, including alphanumeric and other keys for communicating information and/or command selections to the processors 602-606 and/or the one or more sensor testing devices 609. Another type of user input device includes cursor control, such as a mouse, a trackball, or cursor direction keys for communicating direction information and command selections to the processors 602-606 and/or the one or more sensor testing devices 609 and for controlling cursor movement on the display device.
System 600 may include a dynamic storage device, referred to as main memory 616, or a random access memory (RAM) or other computer-readable devices coupled to the processor bus 612 for storing information and instructions to be executed by the processors 602-606 and/or the one or more sensor testing devices 609. Main memory 616 also may be used for storing temporary variables or other intermediate information during execution of instructions by the processors 602-606 and/or the one or more sensor testing devices 609. System 600 may include read-only memory (ROM) and/or other static storage device coupled to the processor bus 612 for storing static information and instructions for the processors 602-606 and/or the one or more sensor testing devices 609. The system outlined in
According to one embodiment, the above techniques may be performed by computer system 600 in response to processor 604 executing one or more sequences of one or more instructions contained in main memory 616. These instructions may be read into main memory 616 from another machine-readable medium, such as a storage device. Execution of the sequences of instructions contained in main memory 616 may cause processors 602-606 and/or the one or more sensor testing devices 609 to perform the process steps described herein. In alternative embodiments, circuitry may be used in place of or in combination with the software instructions. Thus, embodiments of the present disclosure may include both hardware and software components.
Various embodiments may be implemented fully or partially in software and/or firmware. This software and/or firmware may take the form of instructions contained in or on a non-transitory computer-readable storage medium. Those instructions may then be read and executed by one or more processors to enable the performance of the operations described herein. The instructions may be in any suitable form, such as, but not limited to, source code, compiled code, interpreted code, executable code, static code, dynamic code, and the like. Such a computer-readable medium may include any tangible non-transitory medium for storing information in a form readable by one or more computers, such as but not limited to read-only memory (ROM); random access memory (RAM); magnetic disk storage media; optical storage media; a flash memory, etc.
A machine-readable medium includes any mechanism for storing or transmitting information in a form (e.g., software, processing application) readable by a machine (e.g., a computer). Such media may take the form of, but is not limited to, non-volatile media and volatile media and may include removable data storage media, non-removable data storage media, and/or external storage devices made available via a wired or wireless network architecture with such computer program products, including one or more database management products, web server products, application server products, and/or other additional software components. Examples of removable data storage media include Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc Read-Only Memory (DVD-ROM), magneto-optical disks, flash drives, and the like. Examples of non-removable data storage media include internal magnetic hard disks, solid state devices (SSDs), and the like. The one or more memory devices 606 (not shown) may include volatile memory (e.g., dynamic random access memory (DRAM), static random access memory (SRAM), etc.) and/or non-volatile memory (e.g., read-only memory (ROM), flash memory, etc.).
Computer program products containing mechanisms to effectuate the systems and methods in accordance with the presently described technology may reside in main memory 616, which may be referred to as machine-readable media. It will be appreciated that machine-readable media may include any tangible non-transitory medium that is capable of storing or encoding instructions to perform any one or more of the operations of the present disclosure for execution by a machine or that is capable of storing or encoding data structures and/or modules utilized by or associated with such instructions. Machine-readable media may include a single medium or multiple media (e.g., a centralized or distributed database, and/or associated caches and servers) that store the one or more executable instructions or data structures.
Embodiments of the present disclosure include various steps, which are described in this specification. The steps may be performed by hardware components or may be embodied in machine-executable instructions, which may be used to cause a general-purpose or special-purpose processor programmed with the instructions to perform the steps. Alternatively, the steps may be performed by a combination of hardware, software, and/or firmware.
Various modifications and additions can be made to the exemplary embodiments discussed without departing from the scope of the present invention. For example, while the embodiments described above refer to particular features, the scope of this invention also includes embodiments having different combinations of features and embodiments that do not include all of the described features. Accordingly, the scope of the present invention is intended to embrace all such alternatives, modifications, and variations together with all equivalents thereof.
The operations and processes described and shown above may be carried out or performed in any suitable order as desired in various implementations. Additionally, in certain implementations, at least a portion of the operations may be carried out in parallel. Furthermore, in certain implementations, less than or more than the operations described may be performed.
The word “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.
As used herein, unless otherwise specified, the use of the ordinal adjectives “first,” “second,” “third,” etc., to describe a common object, merely indicates that different instances of like objects are being referred to and are not intended to imply that the objects so described must be in a given sequence, either temporally, spatially, in ranking, or any other manner.
It is understood that the above descriptions are for purposes of illustration and are not meant to be limiting.
Although specific embodiments of the disclosure have been described, one of ordinary skill in the art will recognize that numerous other modifications and alternative embodiments are within the scope of the disclosure. For example, any of the functionality and/or processing capabilities described with respect to a particular device or component may be performed by any other device or component. Further, while various illustrative implementations and architectures have been described in accordance with embodiments of the disclosure, one of ordinary skill in the art will appreciate that numerous other modifications to the illustrative implementations and architectures described herein are also within the scope of this disclosure.
Although embodiments have been described in language specific to structural features and/or methodological acts, it is to be understood that the disclosure is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as illustrative forms of implementing the embodiments. Conditional language, such as, among others, “can,” “could,” “might,” or “may,” unless specifically stated otherwise, or otherwise understood within the context as used, is generally intended to convey that certain embodiments could include, while other embodiments do not include, certain features, elements, and/or steps. Thus, such conditional language is not generally intended to imply that features, elements, and/or steps are in any way required for one or more embodiments or that one or more embodiments necessarily include logic for deciding, with or without user input or prompting, whether these features, elements, and/or steps are included or are to be performed in any particular embodiment.
Claims
1. A vehicle sensor testing system, comprising:
- a first plurality of sensor testing targets positioned on a first side of a vehicle at a first distance from the vehicle;
- a second plurality of sensor testing targets positioned on a second side of the vehicle at the first distance from the vehicle, the second side opposite the first side;
- a first sensor testing target positioned at a second distance from the vehicle, the second distance further from the vehicle than the first distance,
- a sixth sensor testing target positioned at a third distance from the vehicle, the third distance different than the first distance and the second distance; and
- wherein the first plurality of sensor testing targets comprises a second sensor testing target associated with first camera data for the vehicle and a third sensor testing target associated with first light detection and ranging (LIDAR) data for the vehicle,
- wherein the second plurality of sensor testing targets comprises a fourth sensor testing target associated with second camera data for the vehicle and a fifth sensor testing target associated with second LIDAR data for the vehicle, and
- wherein the first sensor testing target is associated with at least one of third camera data for the vehicle or third LIDAR data for the vehicle.
2. The vehicle sensor testing system of claim 1, wherein the first plurality of sensor testing targets further comprises a sixth sensor testing target, and wherein the second plurality of sensor testing targets comprises a seventh sensor testing target.
3. The vehicle sensor testing system of claim 1, wherein the first sensor testing target comprises an array of patches.
4. The vehicle sensor testing system of claim 1, wherein the first sensor testing target comprises a first stripe of a first color and a second stripe of a second color.
5. The vehicle sensor testing system of claim 1, further comprising at least one processor configured to:
- receive the first camera data;
- determine that the first camera data fail to satisfy a camera data performance metric; and
- cause presentation of an indication that the first camera data fail to satisfy the camera data performance metric.
6. The vehicle sensor testing system of claim 1, further comprising at least one processor configured to:
- receive the first LIDAR data;
- determine that the first LIDAR data fail to satisfy a LIDAR data performance metric; and
- cause presentation of an indication that the first LIDAR data fail to satisfy the LIDAR data performance metric.
7. The vehicle sensor testing system of claim 1, further comprising at least one processor configured to:
- receive sensor data comprising the first camera data and the first LIDAR data;
- determine an event associated with operation of the vehicle;
- determine that at least one of the first LIDAR data or the first camera data matches a sensor data profile associated with the event; and
- cause presentation of an indication that at least one of the first LIDAR data or the first camera data matches the sensor data profile associated with the event.
8. The vehicle sensor testing system of claim 1, wherein:
- the first camera data is associated with a first camera of the vehicle,
- the second camera data is associated with a second camera of the vehicle,
- the first LID AR data is associated with a first LID AR sensor of the vehicle, and
- the second LID AR data is associated with a second LID AR sensor of the vehicle.
9. The vehicle sensor testing system of claim 1, wherein the first plurality of sensor testing targets are associated with at least one of:
- radar data for the vehicle, thermal data for the vehicle, or acoustic data for the vehicle.
10. A vehicle sensor testing system, comprising:
- a first plurality of sensor testing targets positioned on a first side of a vehicle at a first distance from the vehicle;
- a second plurality of sensor testing targets positioned on a second side of the vehicle at the first distance from the vehicle, the second side opposite the first side;
- a first sensor testing target positioned at a second distance from the vehicle, the second distance further from the vehicle than the first distance
- a sixth sensor testing target positioned at a third distance from the vehicle, the third distance different than the first distance and the second distance; and, wherein the first plurality of sensor testing targets comprises a second sensor testing target associated with first camera data for the vehicle and a third sensor testing target associated with first light detection and ranging (LIDAR) data for the vehicle, wherein the second plurality of sensor testing targets comprises a fourth sensor testing target associated with second camera data for the vehicle and a fifth sensor testing target associated with second LIDAR data for the vehicle, and wherein the first sensor testing target is associated with at least one of third camera data for the vehicle or third LIDAR data for the vehicle, and
- at least one processor coupled to memory, the at least one processor configured to determine, based on at least one of the first camera data, the second camera data, the third camera data, the first LIDAR data, the second LIDAR data, or the third LIDAR data, that a sensor of the vehicle fails to satisfy a vehicle sensor performance metric.
11. The vehicle sensor testing system of claim 10, wherein the first plurality of sensor testing targets further comprises a sixth sensor testing target, and wherein the second plurality of sensor testing targets comprises a seventh sensor testing target.
12. The vehicle sensor testing system of claim 10, wherein the first sensor testing target comprises an array of patches.
13. The vehicle sensor testing system of claim 10, wherein the first sensor testing target comprises a first stripe of a first color and a second stripe of a second color.
14. The vehicle sensor testing system of claim 10, wherein the vehicle sensor performance metric is a camera data performance metric, and wherein to determine that the vehicle sensor fails to satisfy the vehicle sensor performance metric comprises the at least one processor being further configured to:
- receive the first camera data; and
- determine that the first camera data fail to satisfy the camera data performance metric, wherein the at least one processor is further configured to cause presentation of an indication that the first camera data fail to satisfy the camera data performance metric.
15. The vehicle sensor testing system of claim 10, wherein the vehicle sensor performance metric is a LIDAR data performance metric, and wherein to determine that the vehicle sensor fails to satisfy the vehicle sensor performance metric comprises the at least one processor being further configured to:
- receive the first LIDAR data; and
- determine that the first LIDAR data fail to satisfy the LIDAR data performance metric, wherein the at least one processor is further configured to cause presentation of an indication that the first LIDAR data fail to satisfy the LIDAR data performance metric.
16. The vehicle sensor testing system of claim 10, wherein the at least one processor configured to:
- receive sensor data comprising the first camera data and the first LIDAR data;
- determine an event associated with operation of the vehicle;
- determine that at least one of the first LIDAR data or the first camera data matches a sensor data profile associated with the event, wherein to determine that the vehicle sensor fails to satisfy the vehicle sensor performance metric comprises the determination that at least one of the first LIDAR data or the first camera data matches the sensor data profile associated with the event; and
- cause presentation of an indication that at least one of the first LIDAR data or the first camera data matches the sensor data profile associated with the event.
17. A method for vehicle sensor testing, the method comprising:
- receiving, by at least one processor of a device, first camera data associated with a first camera of a vehicle and a first sensor testing target, wherein a first plurality of sensor testing targets comprising the first sensor testing target are positioned on a first side of a vehicle at a first distance from the vehicle;
- receiving, by the at least one processor, second camera data associated with a second camera of the vehicle and a second sensor testing target, wherein a second plurality of sensor testing targets comprising the second sensor testing target are positioned on a second side of the vehicle at the first distance from the vehicle, the second side opposite the first side;
- receiving, by the at least one processor, first light detection and ranging (LIDAR) data associated with a first LIDAR sensor of the vehicle and a third sensor testing target, wherein the first plurality of sensor testing targets comprises the third sensor testing target;
- receiving, by the at least one processor, second LIDAR data associated with a second LIDAR sensor of the vehicle and a fourth sensor testing target, wherein the second plurality of sensor testing targets comprises the fourth sensor testing target;
- receiving, by the at least one processor, at least one of third camera data associated with a third camera of the vehicle or third LIDAR data associated with a third LIDAR sensor of the vehicle, wherein the at least one of the third camera data or the third LIDAR data are associated with a fifth sensor testing target positioned at a second distance from the vehicle, the second distance greater than the first distance;
- receiving, by the at least one processor, at least one of fourth camera data associated with a fourth camera of the vehicle or fourth LIDAR data associated with a fourth LIDAR sensor of the vehicle, wherein the at least one of the fourth camera data or the fourth LIDAR data are associated with a sixth sensor testing target positioned at a third distance from the vehicle, the third distance different than the first distance and the second distance; and
- determining, by the at least one processor, based on at least one of the first camera data, the second camera data, the third camera data, the first LIDAR data, the second LIDAR data, or the third LIDAR data, that a sensor of the vehicle fails to satisfy a vehicle sensor performance metric; and
- cause presentation, by the at least one processor, that that the sensor of the vehicle fails to satisfy the vehicle sensor performance metric.
18. The method for vehicle sensor testing of claim 17 further comprising:
- determining an event associated with operation of the vehicle;
- determining that at least one of the first LIDAR data or the first camera data matches a sensor data profile associated with the event; and
- causing presentation of an indication that at least one of the first LIDAR data or the first camera data matches the sensor data profile associated with the event.
7256818 | August 14, 2007 | Sadok et al. |
7441236 | October 21, 2008 | Chon et al. |
9472097 | October 18, 2016 | Stelzig et al. |
10310509 | June 4, 2019 | Ferguson et al. |
10368063 | July 30, 2019 | Lehmann et al. |
10467704 | November 5, 2019 | Konrardy et al. |
10580227 | March 3, 2020 | Zhai |
11629835 | April 18, 2023 | Kuffner, Jr. |
20090087029 | April 2, 2009 | Coleman et al. |
20090299684 | December 3, 2009 | Imanishi et al. |
20140340570 | November 20, 2014 | Meyers et al. |
20170225680 | August 10, 2017 | Huang |
20170364095 | December 21, 2017 | Wang et al. |
20180075309 | March 15, 2018 | Sathyanarayana |
20180284271 | October 4, 2018 | Bogatscher |
20180297609 | October 18, 2018 | Bozsik |
20180366000 | December 20, 2018 | Wendt et al. |
20190179979 | June 13, 2019 | Melick |
20190204425 | July 4, 2019 | Abari |
20190266712 | August 29, 2019 | Chirayath |
20190351913 | November 21, 2019 | Watanabe |
20200039528 | February 6, 2020 | Ewert |
20200333447 | October 22, 2020 | Cardei |
20210097147 | April 1, 2021 | DeVore |
20210186006 | June 24, 2021 | Sibley |
20210190922 | June 24, 2021 | Yu |
20210192788 | June 24, 2021 | Diederichs |
20210197854 | July 1, 2021 | Grabe |
20210199479 | July 1, 2021 | Lau |
20210208245 | July 8, 2021 | Pandey |
20210208263 | July 8, 2021 | Sutavani |
20210239793 | August 5, 2021 | Yu |
20210278511 | September 9, 2021 | Krishnan |
20210286068 | September 16, 2021 | Kumar |
20210316669 | October 14, 2021 | Wang |
20210318149 | October 14, 2021 | Chang |
20220073036 | March 10, 2022 | Jackson, Jr. |
20220118994 | April 21, 2022 | Lu |
20220326349 | October 13, 2022 | Tone |
10218228 | November 2003 | DE |
102016202805 | August 2017 | DE |
1417512 | January 2019 | EP |
2006287789 | October 2006 | JP |
2018207458 | December 2018 | JP |
2004028134 | April 2004 | WO |
2014172031 | October 2014 | WO |
- International Search Report in corresponding international patent application No. PCT/US2021/05541, dated Jan. 28, 2022, 5 pages.
- Wang et al. “Prognostics of Automotive Sensors: Tools and Case Study”, Proceedings of MFPT 62, Jan. 2008, pp. 1-18, ResearchGate, Berlin, Germany.
- Miller, Christian K. “A Simulation and Regression Testing Framework for Autonomous Vehicles”, Department of Electrical Engineering and Computer Science, Aug. 2007, pp. 1-119, Case Western Reserve University, Cleveland, OH.
- Petit et al. “Remote Attacks on Automated Vehicles Sensors: Experiments on Camera and LiDAR”, Computer Science, Mar. 4, 2019, pp. 1-13, Semantic Scholar, Seattle, Washington.
- Rosnell et al. “Point Cloud Generation from Aerial Image Data Acquired by a Quadrocopter Type Micro Unmanned Aerial Vehicle and a Digital Still Camera”, Sensors, Jan. 4, 2012, pp. 453-480, vol. 12, MDPI, Basel, Switzerland.
Type: Grant
Filed: Oct 23, 2020
Date of Patent: May 28, 2024
Patent Publication Number: 20220130185
Assignee: Argo AI, LLC (Pittsburgh, PA)
Inventors: Michael V. Morelli (Cranbury, NJ), Laurens M. Schouten-Evers (San Francisco, CA), Alan William Yip (Detroit, MI), Duc H. Vu (Sunnyvale, CA), Koji L Gardiner (San Francisco, CA), Christopher N. St. John (Northville, MI), Eric K. Thong (Palo Alto, CA), Morgan M. Wagner (Pittsburgh, PA)
Primary Examiner: Peter D Nolan
Assistant Examiner: Anwar Mohamed
Application Number: 17/079,000
International Classification: G07C 5/08 (20060101); B60W 50/02 (20120101); G01S 7/497 (20060101); G01S 17/931 (20200101); H04N 7/18 (20060101); B60W 60/00 (20200101);